Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements or quotes made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements that assess the reliability or credibility of sources in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.60
    rats
    -0.59
    Contents
    -0.59
    thur
    -0.59
    steamapps
    -0.58
    iosity
    -0.56
    successfully
    -0.55
     diaper
    -0.54
    opus
    -0.53
    eeds
    -0.53
    POSITIVE LOGITS
     said
    0.70
    said
    0.70
     explained
    0.69
     countered
    0.68
     spokesman
    0.66
     analyst
    0.66
     spokeswoman
    0.64
     lamented
    0.63
     Fried
    0.62
     analysts
    0.62
    Act Density 0.372%

    No Known Activations